EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An integrative approach to protein sequence design through multiobjective optimization

Lu Hong iD, Tanja Kortemme iD

PLOS Computational Biology · 11.07.2024 · 20 (7) · e1011953

DOI: 10.1371/journal.pcbi.1011953 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 11.07.2024. Verfasst von Lu Hong und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, California, United States of America. Hauptthemen laut MEDLINE: Algorithms, Computational Biology, Proteins. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 129 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, nigms.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With recent methodological advances in the field of computational protein design, in particular those based on deep learning, there is an increasing need for frameworks that allow for coherent, direct integration of different models and objective functions into the generative design process. Here we demonstrate how evolutionary multiobjective optimization techniques can be adapted to provide such an approach. With the established Non-dominated Sorting Genetic Algorithm II (NSGA-II) as the optimization framework, we use AlphaFold2 and ProteinMPNN confidence metrics to define the objective space, and a mutation operator composed of ESM-1v and ProteinMPNN to rank and then redesign the least favorable positions. Using the two-state design problem of the foldswitching protein RfaH as an in-depth case study, and PapD and calmodulin as examples of higher-dimensional design problems, we show that the evolutionary multiobjective optimization approach leads to significant reduction in the bias and variance in RfaH native sequence recovery, compared to a direct application of ProteinMPNN. We suggest that this improvement is due to three factors: (i) the use of an informative mutation operator that accelerates the sequence space exploration, (ii) the parallel, iterative design process inherent to the genetic algorithm that improves upon the ProteinMPNN autoregressive sequence decoding scheme, and (iii) the explicit approximation of the Pareto front that leads to optimal design candidates representing diverse tradeoff conditions. We anticipate this approach to be readily adaptable to different models and broadly relevant for protein design tasks with complex specifications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsComputational BiologyProteinsAmino Acid SequenceProtein EngineeringSequence Analysis, Protein

Substanzen

Proteins

Autor:innen und Institutionen

  • Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, California, United States of America.
  • Quantitative Biosciences Institute, University of California, San Francisco, California, United States of America.
  • Chan Zuckerberg Biohub, San Francisco, California, United States of America.

ORCID-Profile: Lu Hong, Tanja Kortemme

Förderung

  • NIGMS NIH HHS
  • nigms

Zitieren

APA

Hong, L., & Kortemme, T. (2024). An integrative approach to protein sequence design through multiobjective optimization. PLOS Computational Biology, 20(7), e1011953. https://doi.org/10.1371/journal.pcbi.1011953

Vancouver

Hong L, Kortemme T. An integrative approach to protein sequence design through multiobjective optimization. PLOS Computational Biology. 2024;20(7):e1011953. doi:10.1371/journal.pcbi.1011953

BibTeX
@article{Hong2024,
  author = {Hong, Lu and Kortemme, Tanja},
  title = {An integrative approach to protein sequence design through multiobjective optimization},
  journal = {PLOS Computational Biology},
  year = {2024},
  volume = {20},
  number = {7},
  pages = {e1011953},
  doi = {10.1371/journal.pcbi.1011953}
}
Kostenlos starten →